论文标题
响应期间的记忆，以响应生成中的按需知识集成
Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
论文作者
论文摘要
已知神经对话模型总体上会产生适当但非信息的反应。通过阅读（CBR），可以对信息进行显着增强信息的方案，与给定的外部文档进行对话。在以前的工作中，外部文档是通过（1）创建上下文感知文档内存来使用的，该文档记忆积分从文档和对话上下文中集成了信息，然后（2）生成涉及内存的响应。在本文中，我们建议创建文档内存，并考虑到一些预期的响应。这是使用教师学生框架实现的。为教师提供了外部文档，上下文和基础真相的响应，并学习如何从三个信息来源构建响应感知文档记忆。学生学会从前两个来源构建响应期间的文档内存，以及老师对记忆创造的见解。经验结果表明，我们的模型的表现优于先前的CBR任务。
Neural conversation models are known to generate appropriate but non-informative responses in general. A scenario where informativeness can be significantly enhanced is Conversing by Reading (CbR), where conversations take place with respect to a given external document. In previous work, the external document is utilized by (1) creating a context-aware document memory that integrates information from the document and the conversational context, and then (2) generating responses referring to the memory. In this paper, we propose to create the document memory with some anticipated responses in mind. This is achieved using a teacher-student framework. The teacher is given the external document, the context, and the ground-truth response, and learns how to build a response-aware document memory from three sources of information. The student learns to construct a response-anticipated document memory from the first two sources, and the teacher's insight on memory creation. Empirical results show that our model outperforms the previous state-of-the-art for the CbR task.
